The Prevalence and Prediction of Uncontrolled Type 2 Diabetes Mellitus in the Lower South of Thailand

Authors

Akemat Wongpairin, Department of Mathematics and Computer Science, Faculty of Science and Technology, Prince of Songkla University, Pattani Campus, 94000, Thailand.
Apiradee Lim, Department of Mathematics and Computer Science, Faculty of Science and Technology, Prince of Songkla University, Pattani Campus, 94000, Thailand.Follow
Haris Khurram, Department of Mathematics and Computer Science, Faculty of Science and Technology, Prince of Songkla University, Pattani Campus, 94000, Thailand.

Abstract

Background: Type 2 diabetes (T2DM) is a major health issue globally, particularly in middle-income countries. This study assessed the prevalence and factors linked to uncontrolled T2DM and proposed a machine learning model for early prediction in southern Thailand.

Methods: Data from 60,903 T2DM patients (2016–2023) were obtained from Thailand's National Health Data Center. Multiple logistic regression identified associated factors, and machine learning models were compared for prediction.

Results: Uncontrolled T2DM prevalence was 53.5%, highest among patients ≤44 years (69.5%) and in Pattani (61.6%), Satun (58.1%), and Narathiwat (56.7%). Risk factors included being female, younger age, early or long disease duration, overweight, and no hypertension. Among models, random forest showed the highest accuracy (83.7%) and neural networks the highest sensitivity (52.6%).

Conclusion: Targeted interventions are needed to address uncontrolled T2DM in southern Thailand. Random forest is the most accurate model for early prediction, supporting efforts to reduce disease burden.

Keywords: Diabetes mellitus, Machine learning, Prediction, Thailand

Recommended Citation

Wongpairin A, Lim A, Khurram H. The Prevalence and Prediction of Uncontrolled Type 2 Diabetes Mellitus in the Lower South of Thailand. J Health Res. 2025; 39(3):-. DOI: https://doi.org/10.56808/2586-940X.1144

References

[1] NCD Risk Factor Collaboration (NCD-RisC). Worldwide trends in diabetes prevalence and treatment from 1990 to 2022: a pooled analysis of 1108 population-representative studies with 141 million participants. Lancet 2024 Nov 23; 404(10467):2077e93. https://doi.org/10.1016/S0140-6736(24)02317-1.

[2] Green A, Hede SM, Patterson CC, Wild SH, Imperatore G, Roglic G, et al. Type 1 diabetes in 2017: global estimates of incident and prevalent cases in children and adults. Diabetologia 2021 Dec;64(12):2741e50. https://doi.org/10.1007/s00125-021-05571-8.

[3] Hossain MJ, Al-Mamun M, Islam MR. Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused. Health Sci Rep 2024 Mar 22;7(3):e2004. https://doi.org/10.1002/hsr2.2004.

[4] Blonde L, Aschner P, Bailey C, Ji L, Leiter LA, Matthaei S, et al. Gaps and barriers in the control of blood glucose in people with type 2 diabetes. Diabetes Vasc Dis Res 2017 May; 14(3):172e83. https://doi.org/10.1177/1479164116679775.

[5] Ismail IM, Naik PR. Prevalence and determinants of uncontrolled diabetes mellitus: a community-based study from Karnataka, India. Natl J Community Med 2024 Oct;15(10): 842e9. https://doi.org/10.55489/njcm.151020244459.

[6] Akter F, Alam SMU,HasanMM,RanaMM,ChowdhuryNA, Karim M, et al. Prevalence of uncontrolled Type 2 Diabetes Mellitus and its associated factors among people within southern part of Bangladesh. Chittagong Med Coll Teach Assoc 2019 Jan;30(2):92e8. https://doi.org/10.3329/jcmcta.v30i2.62593.

[7] Dusabeyezu S, Renzaho JN, Sani N. Prevalence and factors associated with uncontrolled type 2 diabetes among patients in Kirehe District, Rwanda: a cross-sectional study. Pan Afr Med J 2024 Jul 24;48:128. https://doi.org/10.11604/pamj.2024.48.128.43864.

[8] Gebreziher LH, Beyene MG, Mekonnen D, Baye AM. Predictors of uncontrolled hypertension among type 2 diabetic patients in Ethiopia: Multicenter cross-sectional study. Int J Cardiol Cardiovasc Risk Prev 2024 Jul 4;22:200308. https://doi.org/10.1016/j.ijcrp.2024.200308.

[9] Adeniyi OV, Yogeswaran P, Longo-Mbenza B, Ter Goon D, Ajayi AI. Cross-sectional study of patients with type 2 diabetes in OR Tambo district, South Africa. BMJ Open 2016 Jul 29;6(7):e010875. https://doi.org/10.1136/bmjopen-2015-010875.

[10] Magliano DJ, Boyko EJ, Genitsaridi I, Piemonte L, Riley P, Salpea P. IDF diabetes atlas. In: Report : diabetes and COVID-19: the role of glycaemic control, diabetes subtype and blood glucose on COVID-19 severity and death. Brussels: International Diabetes Federation; 2022.

[11] Puangpet T, Pongkunakorn T, Chulkarat N, Bunlangjit C, Surawit A, Pinsawas B, et al. Control and complications of diabetes in urban primary care units in Thailand: a crosssectional study. BMC Prim Care 2022 Aug 22;23(1):212. https://doi.org/10.1186/s12875-022-01823-7.

[12] Lertwanichwattana T, Suwannahitatorn P, Mungthin M, Rangsin R. Prognostic nomogram for uncontrolled type 2 diabetes using Thailand nation-wide cross-sectional studies. PLoS One 2024 Apr 10;19(4):e0298010. https://doi.org/10.1371/journal.pone.0298010.

[13] Yeemard F, Srichan P, Apidechkul T, Luerueang N, Tamornpark R, Utsaha S. Prevalence and predictors of suboptimal glycemic control among patients with type 2 diabetes mellitus in northern Thailand: A hospital-based crosssectional control study. PLoS One 2022 Jan 18;17(1):e0262714. https://doi.org/10.1371/journal.pone.0262714.

[14] Phuwilert P, Khiewkhern S, Wongprachum K, Phajan T. Google maps: prevalence and distribution of uncontrolled type 2 diabetes mellitus in Kalasin Province, Thailand. Stud Health Technol Inform 2020 Jun 26;272:403e6. https://doi.org/10.3233/SHTI200580.

[15] Somanawat J, Saramunee K, Chanasopon S. Process, quality and challenges of diabetes care in primary care: a study of district health network in Thailand. Prim Health Care Res Dev 2020 Oct 27;21:e46. https://doi.org/10.1017/S1463423620000468.

[16] American Diabetes Association. Standards of care in diabetes 2023. Diabetes Care 2023 Jan;46:S1e267.

[17] Tongkumchum P, McNeil D. Confidence intervals using contrasts for regression model. Songklanakarin J Sci Technol 2009 Mar e Apr;31(2):151e6.

[18] R CoreTeam. R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing; 2023.

[19] Sakboonyarat B, Pima W, Chokbumrungsuk C, Pimpak T, Khunsri S, Ukritchon S, et al. National trends in the prevalence of glycemic control among patients with type 2 diabetes receiving continuous care in Thailand from 2011 to 2018. Sci Rep 2021 Jul 12;11(1):14260. https://doi.org/10.1038/s41598-021-93733-4.

[20] Najafipour H, Farjami M, Sanjari M, Amirzadeh R, Shadkam Farokhi M, Mirzazadeh A. Prevalence and incidence rate of diabetes, pre-diabetes, uncontrolled diabetes, and their predictors in the adult population in Southeastern Iran: Findings From KERCADR Study. Front Public Health 2021 Nov 1;9:611652. https://doi.org/10.3389/fpubh.2021.611652.

[21] Vu GT, Shakib S, King C, Gurupur V, Little BB. Association between uncontrolled diabetes and periodontal disease in US adults: NHANES 2009-2014. Sci Rep 2023 Oct 4;13(1): 16694. https://doi.org/10.1038/s41598-023-43827-y.

[22] Rubio-Almanza M, Camara-Gomez R, Merino-Torres JF. Obesity and type 2 diabetes: Also linked in therapeutic options. Endocrinol Diabetes Nutr (Engl Ed) 2019 Mar;66(3): 140e9. https://doi.org/10.1016/j.endinu.2018.08.003. English, Spanish.

[23] Ling C, R€ onn T. Epigenetics in human obesity and type 2 diabetes. Cell Metab 2019 May 7;29(5):1028e44. https://doi.org/10.1016/j.cmet.2019.03.009.

[24] Anusuya GS, Ravi R, Gopalakrishnan S, Abiselvi A, Stephen T. Prevalence of undiagnosed and uncontrolled diabetes mellitus among adults in South Chennai. Int J Community Med Public Health 2018 Dec;5(12):5200e4. https://doi.org/10.18203/2394-6040.ijcmph20184790.

[25] Cannon A, Handelsman Y, Heile M, Shannon M. Burden of illness in type 2 diabetes mellitus. J Manag Care Spec Pharm 2018 Sep;24(9-a Suppl):S5e13. https://doi.org/10.18553/jmcp.2018.24.9-a.s5.

[26] Davies MJ, D'Alessio DA, Fradkin J, Kernan WN, Mathieu C, Mingrone G, et al. Management of hyperglycemia in type 2 diabetes, 2018. A consensus report by the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). Diabetes Care 2018 Dec;41(12): 2669e701. https://doi.org/10.2337/dci18-0033.

[27] Mehta S, Mocarski M, Wisniewski T, Gillespie K, Narayan KMV, Lang K. Primary care physicians' utilization of type 2 diabetes screening guidelines and referrals to behavioral interventions: a survey-linked retrospective study. BMJ Open Diabetes Res Care 2017 Aug 11;5(1): e000406. https://doi.org/10.1136/bmjdrc-2017-000406.

[28] Hockett CW, Praveen PA, Ong TC, Amutha A, Isom SP, Jensen ET, et al. Clinical profile at diagnosis with youthonset type 1 and type 2 diabetes in two pediatric diabetes registries: SEARCH (United States) and YDR (India). Pediatr Diabetes 2021 Feb;22(1):22e30. https://doi.org/10.1111/pedi.12981.

[29] Siller AF, Tosur M, Relan S, Astudillo M, McKay S, Dabelea D, et al. Challenges in the diagnosis of diabetes type in pediatrics. Pediatr Diabetes 2020 Nov;21(7):1064e73. https://doi.org/10.1111/pedi.13070.

[30] Catapan SC, Nair U, Gray L, Cristina Marino Calvo M, Bird D, Janda M, et al. Same goals, different challenges: A systematic review of perspectives of people with diabetes and healthcare professionals on Type 2 diabetes care. Diabet Med 2021 Sep;38(9):e14625. https://doi.org/10.1111/dme.14625.

[31] Jørgensen PG, Jensen MT, Biering-Sørensen T, Mogelvang R, Fritz-Hansen T, Vilsbøll T, et al. Burden of uncontrolled metabolic risk factors and left ventricular structure and function in patients with type 2 diabetes mellitus. J Am Heart Assoc 2018 Oct 2;7(19):e008856. https://doi.org/10.1161/JAHA.118.008856.

[32] Sunil B, Ashraf AP. Dyslipidemia in pediatric type 2 diabetes mellitus. Curr Diabetes Rep 2020 Sep 9;20(10):53. https://doi.org/10.1007/s11892-020-01336-6.

[33] Ikramuddin S, Korner J, Lee WJ, Thomas AJ, Connett JE, Bantle JP, et al. Lifestyle Intervention and medical management with vs without roux-en-y gastric bypass and control of hemoglobin A1c, LDL cholesterol, and systolic blood pressure at 5 years in the diabetes surgery study. JAMA 2018 Jan 16;319(3):266e78. https://doi.org/10.1001/jama.2017.20813.

[34] Holtrop J, Spiering W, Nathoe HM, De Borst GJ, Kappelle LJ, De Valk HW, et al. Apparent therapy-resistant hypertension as risk factor for the development of type 2 diabetes mellitus. J Hypertens 2020 Jan;38(1):45e51. https://doi.org/10.1097/HJH.0000000000002227.

[35] Mancusi C, Izzo R, di Gioia G, Losi MA, Barbato E, Morisco C. Insulin resistance the hinge between hypertension and type 2 diabetes. High Blood Press Cardiovasc Prev 2020 Dec;27(6):515e26. https://doi.org/10.1007/s40292-020-00408-8.

[36] Almalki ZS, Albassam AA, Alhejji NS, Alotaibi BS, AlOqayli LA, Ahmed NJ. Prevalence, risk factors, and management of uncontrolled hypertension among patients with diabetes: A hospital-based cross-sectional study. Prim Care Diabetes 2020 Dec;14(6):610e5. https://doi.org/10.1016/j.pcd.2020.02.004.

[37] Wallace ML, Mentch L, Wheeler BJ, Tapia AL, Richards M, Zhou S, et al. Use and misuse of random forest variable importance metrics in medicine: demonstrations through incident stroke prediction. BMC Med Res Methodol 2023 Jun 19;23(1):144. https://doi.org/10.1186/s12874-023-01965-x.

[38] Lim A, Taufik MR, Tongkumchum P, Dureh N. Comparison of different supervised machine learning algorithms for the prediction of tuberculosis mortality. Adv Appl Stat 2020 May; 62(2):185e201. https://doi.org/10.17654/AS062020185.

[39] Telalovic Hasic J, Salkovic A. Breast cancer classification using support vector machines (SVM). In: International symposium on innovative and interdisciplinary applications of advanced technologies. Cham: Springer Nature Switzerland; 2023.

[40] Shahid S, Khurram H, Lim A, Shabbir MF, Billah B. Prediction of cyanotic and acyanotic congenital heart disease using machine learning models. World J Clin Pediatr 2024 Dec 9;13(4):98472. https://doi.org/10.5409/wjcp.v13.i4.98472.

[41] Adua E, Kolog EA, Afrifa-Yamoah E, Amankwah B, Obirikorang C, Anto EO, et al. Predictive model and feature importance for early detection of type II diabetes mellitus. Transl Med Commun 2021;6(17):1e15. https://doi.org/10.1186/s41231-021-00096-z.